Standard Article

Total Expected Discounted Reward MDPS: Existence of Optimal Policies

  1. Eugene A. Feinberg

Published Online: 15 FEB 2011

DOI: 10.1002/9780470400531.eorms0906

Wiley Encyclopedia of Operations Research and Management Science

Wiley Encyclopedia of Operations Research and Management Science

How to Cite

Feinberg, E. A. 2011. Total Expected Discounted Reward MDPS: Existence of Optimal Policies. Wiley Encyclopedia of Operations Research and Management Science. .

Author Information

  1. State University of New York at Stony Brook, Department of Applied Mathematics and Statistics, Stony Brook, New York

Publication History

  1. Published Online: 15 FEB 2011

Abstract

This article describes the results on the existence of optimal and nearly optimal policies for Markov Decision Processes (MDPs) with total expected discounted rewards. The problem of optimization of total expected discounted rewards for MDPs is also known under the name of discounted dynamic programming.

Keywords:

  • Markov decision process;
  • dynamic programming;
  • reward function;
  • optimal policy;
  • discounted rewards